Login / Signup
Producing efficient error-bounded solutions for transition independent decentralized mdps.
Jilles Steeve Dibangoye
Christopher Amato
Arnaud Doniec
François Charpillet
Published in:
AAMAS (2013)
Keyphrases
</>
markov decision processes
cost effective
reinforcement learning
cooperative
efficient solutions
multi agent
efficient computation
state space
error rate
markov chain
dec pomdps
benchmark problems
computationally expensive
optimal policy
neural network
peer to peer
multi objective
lower bound
machine learning